io.github.AceDataCloud/mcp-maestro

Maestro MCP Server

Produce complete videos from a natural-language brief with Maestro through the Ace Data Cloud API. Maestro plans the script, creates or sources media, generates voiceover and music, edits, captions, renders, and returns finished video variants.

Install

pip install mcp-maestro
export ACEDATACLOUD_API_TOKEN="your-token"
mcp-maestro

Get an API token from platform.acedata.cloud.

For a hosted connection, use https://maestro.mcp.acedata.cloud/mcp. It accepts a direct Ace Data Cloud Bearer token and supports OAuth sign-in.

Tools

Tool	Purpose
maestro_create_video	Create a video or run remix, edit, or extend on an earlier task
maestro_get_task	Read progress, status, and final language variants for one task
maestro_list_tasks	List the authenticated account's recent tasks, newest first

Example

Ask an MCP client:

Create a 45-second 16:9 English product launch video from this product photo. Use an editorial style and a documentary voice.

The tool returns a task_id immediately. Query that ID until status is succeeded or failed. Successful tasks expose videos in response.data.variants.

To inspect existing task history without creating a video, call maestro_list_tasks. It accepts a limit from 1 to 100 and optional exclusive created_at_min / created_at_max Unix timestamp bounds. The returned items honor those filters; count remains the authenticated account's total visible task count.

Production contract

Maestro provides the complete capability set on every request: all actions and scenarios, 5–300 seconds, up to 4 languages, and 1080p/30fps output. The base price is 0.60 Credits per delivered second. Avatar uses a 1.15× scenario multiplier, drama uses 1.35×, and each additional delivered language adds 6 Credits. Failed tasks and task polling are free.

To revise an existing result, call maestro_create_video with an iteration action and the prior task ID:

{
  "prompt": "Keep the visuals but tighten the first 10 seconds and use a warmer voice.",
  "action": "edit",
  "ref_task_id": "previous-task-id"
}

MCP Client Configuration

{
  "mcpServers": {
    "maestro": {
      "command": "uvx",
      "args": ["mcp-maestro"],
      "env": {
        "ACEDATACLOUD_API_TOKEN": "your-token"
      }
    }
  }
}

Development

pip install -e ".[dev,test,release]"
pytest --cov=core --cov=tools
ruff check .
ruff format --check .
mypy core tools main.py
python -m build

See the Maestro API documentation for billing and response details.

Documentation

Documentation